Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to legal or procedural terminology

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isha
    -0.73
     contrace
    -0.70
    ishi
    -0.69
     foremost
    -0.68
    izont
    -0.67
    jew
    -0.63
    asha
    -0.63
     Belg
    -0.62
     motto
    -0.61
    ISH
    -0.61
    POSITIVE LOGITS
    umbnail
    0.98
    ragon
    0.92
    ures
    0.85
    e
    0.85
    enced
    0.82
    vous
    0.81
    ornia
    0.81
    ure
    0.74
    uits
    0.74
    inct
    0.74
    Act Density 0.028%

    No Known Activations